Multi-task faster R-CNN for nighttime pedestrian detection and distance estimation

Dai, Xiaobiao; Hu, Junping; Zhang, Hongmei; Abubakar, Shitu; Luo, Cheng; Osman, Ahmad; Сфарра, Стефано; Duan, Yuxia

doi:10.1016/j.infrared.2021.103694

Cited by 37 publications

(13 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, the Fast R-CNN oversees the process of detection and classification of the tools in Free and Occlusion categories, which allow to know when there are stacked elements (Occlusion) and when not (Free). In [29], a similar case based on distance information and faster R-CNN is showed, illustrating how this network improves object detection using a region of interest ROI. That condition allows knowing object location in complement to the fine-tune discrimination of the DAG-CNN.…”

Section: Methodsmentioning

confidence: 99%

Classification and Grip of Occluded Objects

Moreno

Useche-Murillo

2021

IJEEI

View full text Add to dashboard Cite

The present paper exposes a system for detection, classification, and grip of occluded objects by machine vision, artificial intelligence, and an anthropomorphic robot, to generate a solution for the subjection of elements that present occlusions. The deep learning algorithm used is based on Convolutional Neural Networks (CNN), specifically Fast R-CNN (Fast Region-Based CNN) and DAG-CNN (Directed Acyclic Graph CNN) for pattern recognition, the three-dimensional information of the environment was collected through Kinect V1, and tests simulations by the tool VRML. A sequence of detection, classification, and grip was programmed to determine which elements present occlusions and which type of tool generates the occlusion. According to the user's requirements, the desired elements are delivered (occluded or not), and the unwanted elements are removed. It was possible to develop a program with 88.89% accuracy in gripping and delivering occluded objects using networks Fast R-CNN and DAG-CNN with achieving of 70.9% and 96.2% accuracy respectively, detecting elements without occlusions for the first net and classifying the objects into five tools (Scalpel, Scissor, Screwdriver, Spanner, and Pliers), with the second net. The grip of occluded objects requires accurate detection of the element located at the top of the pile of objects to remove it without affecting the rest of the environment. Additionally, the detection process requires that a part of the occluded tool be visible to determine the existence of occlusions in the stack.

show abstract

Section: Methodsmentioning

confidence: 99%

Classification and Grip of Occluded Objects

Moreno

Useche-Murillo

2021

IJEEI

View full text Add to dashboard Cite

show abstract

“…e development process of the R-CNN algorithm is shown in Figure 1, from R-CNN [22], Fast R-CNN [23], Faster R-CNN [24] to the most advanced Mask R-CNN [25] algorithm at present, which is manifested in the continuous improvement of precision and speed, covering various fields from classification to detection, segmentation and positioning [26][27][28][29][30]. e two-stage detection has high detection precision and strong robustness, but the detection speed is slow.…”

Section: Methodsmentioning

confidence: 99%

X-Ray Image Recognition Based on Improved Mask R-CNN Algorithm

Zhang

Song

Feng

et al. 2021

Mathematical Problems in Engineering

View full text Add to dashboard Cite

It is an important part of security inspection to carry out security and safety screening with X-ray scanners. Computer vision plays an important role in detection, recognition, and location analysis in intelligent manufacturing. The object detection algorithm is an important part of the intelligent X-ray machine. Existing threat object detection algorithms in X-ray images have low detection precision and are prone to missed and false detection. In order to increase the precision, a new improved Mask R-CNN algorithm is proposed in this paper. In the feature extraction network, an enhancement path is added to fuse the features of the lower layer into the higher layer, which reduces the loss of feature information. By adding an edge detection module, the training effect of the sample model can be improved without accurate labeling. The distance, overlap rate, and scale difference between objects and region proposals are solved using DIoU to improve the stability of the region proposal’s regression, thus improving the accuracy of object detection; SoftNMS algorithm is used to overcome the problem of missed detection when the objects to be detected overlap each other. The experimental results indicate that the mean Average Precision (mAP) of the improved algorithm is 9.32% higher than that of the Mask R-CNN algorithm, especially for knife and portable batteries, which are small in size, simple in shape, and easy to be mistakenly detected, and the Average Precision (AP) is increased by 13.41% and 15.92%, respectively. The results of the study have important implications for the practical application of threat object detection in X-ray images.

show abstract

“…considered the feature differences between thermal infrared images and RGB images, discussed in depth six convolutional networks of different scales, and proposed a light-perception Faster R-CNN detection framework. Similarly, Dai and Hu et al [ 17 ] proposed a novel multitask Faster R-CNN detector to estimate the safe driving distance to improve the precision of driving only, which adjusts the ResNet-50 feature extractor. Realize distance evaluation while improving feature characterization capabilities.…”

Section: Related Workmentioning

confidence: 99%

Non-GDANets: Sports small object detection of thermal images with Non-Glodal decoupled Attention

Zhao¹,

Mao²,

Meng³

et al. 2022

PLoS ONE

View full text Add to dashboard Cite

Because thermal infrared sport targets have rich and complex semantic information, there is a high coupling between different types of features. In view of these limitations, we propose a Non-Glodal decoupled Attention, namely,local U-shaped attention decoupling network (LUANets), which aims to decompose the coupling relationship of different sport target features in thermal infrared images and establish effective spatial dependence between them. This method takes the captured multi-scale initial features according to different levels and inputs them into the local decoupling module with U-shaped attention structure to realize the decomposition of semantic details. At the same time, considering the correlation between different targets, in the process of feature decomposition, using prior knowledge as guiding information many times to establish effective spatial dependence. Secondly, we design a two-way cross-aggregation FPN module to cross-aggregate information flows in the front and back directions to achieve feature interaction while further reducing the coupling between different types of features. The evaluation results on data such as TIIs,SportFCs and FLIR show that the LUANets method we proposed has achieved the best detection performance, with mAP of 68.72%,59.51% and 65.29%, respectively.

show abstract

Multi-task faster R-CNN for nighttime pedestrian detection and distance estimation

Cited by 37 publications

References 46 publications

Classification and Grip of Occluded Objects

Classification and Grip of Occluded Objects

X-Ray Image Recognition Based on Improved Mask R-CNN Algorithm

Non-GDANets: Sports small object detection of thermal images with Non-Glodal decoupled Attention

Contact Info

Product

Resources

About